Circulant Binary Embedding
Authors: Felix Yu, Sanjiv Kumar, Yunchao Gong, Shih-Fu Chang
ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show by extensive experiments that the proposed approach gives much better performance than the state-of-the-art approaches for fixed time, and provides much faster computation with no performance degradation for fixed number of bits. |
| Researcher Affiliation | Collaboration | 1Columbia University, New York, NY 10027 2Google Research, New York, NY 10011 3University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 |
| Pseudocode | No | The paper describes the optimization procedure step-by-step but does not present it in a formally structured pseudocode block or an algorithm environment. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code or provide links to a code repository for the methodology described. |
| Open Datasets | Yes | The Flickr-25600 dataset contains 100K images sampled from a noisy Internet image collection. Each image is represented by a 25, 600 dimensional vector. The Image Net-51200 contains 100k images sampled from 100 random classes from Image Net (Deng et al., 2009), each represented by a 51, 200 dimensional vector. The third dataset (Image Net-25600) is another random subset of Image Net containing 100K images in 25, 600 dimensional space. |
| Dataset Splits | Yes | We use Image Net-25600, with randomly sampled 100 images per category for training, 50 for validation and 50 for testing. |
| Hardware Specification | Yes | The time is based on a single 2.9GHz CPU core. |
| Software Dependencies | No | The paper mentions 'FFT algorithms' and 'highly optimized FFT libraries' but does not specify any software names with version numbers required for reproducibility. |
| Experiment Setup | Yes | The proposed CBE method is found robust to the choice of λ in (15). For example, in the retrieval experiments, the performance difference for λ = 0.1, 1, 10, is within 0.5%. Therefore, in all the experiments, we simply fix λ = 1. |